A deep data augmentation framework based on generative adversarial networks

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

6 Scopus Citations
View graph of relations

Author(s)

  • Qiping Wang
  • Ling Luo
  • Haoran Xie
  • Yanghui Rao
  • Detian Zhang

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)42871–42887
Journal / PublicationMultimedia Tools and Applications
Volume81
Issue number29
Online published13 Aug 2022
Publication statusPublished - Dec 2022

Link(s)

Abstract

In the process of training convolutional neural networks, the training data is often insufficient to obtain ideal performance and encounters the overfitting problem. To address this issue, traditional data augmentation (DA) techniques, which are designed manually based on empirical results, are often adopted in supervised learning. Essentially, traditional DA techniques are in the implicit form of feature engineering. The augmentation strategies should be designed carefully, for example, the distribution of augmented samples should be close to the original data distribution. Otherwise, it will reduce the performance on the test set. Instead of designing augmentation strategies manually, we propose to learn the data distribution directly. New samples can then be generated from the estimated data distribution. Specifically, a deep DA framework is proposed which consists of two neural networks. One is a generative adversarial network, which is used to learn the data distribution, and the other one is a convolutional neural network classifier. We evaluate the proposed model on a handwritten Chinese character dataset and a digit dataset, and the experimental results show it outperforms baseline methods including one manually well-designed DA method and two state-of-the-art DA methods.

Research Area(s)

  • Data augmentation, Convolutional neural networks, Generative adversarial networks, RECOGNITION

Bibliographic Note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Citation Format(s)

A deep data augmentation framework based on generative adversarial networks. / Wang, Qiping; Luo, Ling; Xie, Haoran et al.
In: Multimedia Tools and Applications, Vol. 81, No. 29, 12.2022, p. 42871–42887.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

Download Statistics

No data available